Triple

T38489224
Position Surface form Disambiguated ID Type / Status
Subject HarbourFront E918006 entity
Predicate hasCruiseFacility P190079 FINISHED
Object international cruise terminal at Singapore Cruise Centre LITERAL FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: international cruise terminal at Singapore Cruise Centre | Statement: [HarbourFront, hasCruiseFacility, international cruise terminal at Singapore Cruise Centre]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasCruiseFacility
Context triple: [HarbourFront, hasCruiseFacility, international cruise terminal at Singapore Cruise Centre]
  • A. hasCruiseFacilities chosen
    Indicates that a location or entity provides facilities or infrastructure to support cruise ships or cruise-related activities.
  • B. cruiseCapability
    Indicates the ability of an entity to travel or operate in a steady, sustained cruising mode under its own power.
  • C. hasCruiseDeparturePoint
    Indicates the location from which a cruise journey is scheduled to start or depart.
  • D. servesCruisePort
    Indicates that one entity (typically a transportation service or route) provides service to or operates at a particular cruise port.
  • E. hasCruiseTraffic
    Indicates that there is cruise ship traffic occurring at or involving a particular location or route.
  • F. None of above.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69f76e9894208190a129a553a60ca58c completed May 3, 2026, 3:49 p.m.
NER Named-entity recognition batch_69fd7fdafbe881908a31fcb407af2c34 completed May 8, 2026, 6:16 a.m.
PD Predicate disambiguation batch_69fd7ef0ea908190b5d83f71565bdb1c completed May 8, 2026, 6:13 a.m.
Created at: May 3, 2026, 4:31 p.m.